{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T04:50:15Z","timestamp":1766724615907,"version":"3.48.0"},"reference-count":25,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T00:00:00Z","timestamp":1766620800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: High-risk (B3) breast lesions are a heterogeneous group with uncertain malignant potential. Methods: We systematically reviewed and meta-analyzed the ability of artificial-intelligence (AI) models to predict malignant upgrades (a ductal carcinoma in situ or an invasive carcinoma) after biopsy. A comprehensive search of medical and engineering databases through 27 July 2025 identified retrospective studies that developed or validated AI models for upgrade prediction in cohorts with \u226520 B3 lesions and confirmed outcomes at surgical excision or after \u226524 months of follow-up. Results: Three single-center studies (557 lesions, 91 upgrades) met the eligibility criteria. Pooled analysis focused on clinically meaningful operating points rather than raw accuracy metrics. Models tuned for high sensitivity achieved high negative predictive values (pooled 0.95), suggesting reliable identification of lesions suitable for surveillance, but positive predictive values were modest and heterogenous (0.15\u20131.00), reflecting trade-offs between avoiding missed upgrades and reducing unnecessary excisions. Only two studies reported area-under-the-receiver-operating-characteristic curves, which pooled to 0.72, indicating moderate discrimination. Conclusions: Although limited by small sample sizes and single-center designs, these findings suggest that AI could aid decision-making for B3 lesion management. Prospective multicenter validation and standardized reporting are needed to evaluate clinical utility.<\/jats:p>","DOI":"10.3390\/diagnostics16010075","type":"journal-article","created":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T03:06:02Z","timestamp":1766718362000},"page":"75","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Diagnostic Performance of Artificial Intelligence in Predicting Malignant Upgrade of B3 Breast Lesions: Systematic Review and Meta-Analysis"],"prefix":"10.3390","volume":"16","author":[{"given":"Romuald","family":"Ferre","sequence":"first","affiliation":[{"name":"Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5509-2948","authenticated-orcid":false,"given":"Cherie M.","family":"Kuzmiak","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.ejso.2018.12.008","article-title":"High risk (B3) breast lesions: What is the incidence of malignancy for individual lesion subtypes? A systematic review and meta-analysis","volume":"45","author":"Forester","year":"2019","journal-title":"Eur. J. Surg. Oncol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/s10549-018-05071-1","article-title":"Second International Consensus Conference on lesions of uncertain malignant potential in the breast (B3 lesions)","volume":"174","author":"Rageth","year":"2019","journal-title":"Breast Cancer Res. Treat."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s00428-023-03566-x","article-title":"Third International Consensus Conference on lesions of uncertain malignant potential in the breast (B3 lesions)","volume":"483","author":"Elfgen","year":"2023","journal-title":"Virchows Arch."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"D\u2019archi, S., Carnassale, B., Sanchez, A.M., Accetta, C., Belli, P., De Lauretis, F., Di Guglielmo, E., Di Leone, A., Franco, A., and Magno, S. (2025). Navigating the uncertainty of B3 breast lesions: Diagnostic challenges and evolving management strategies. J. Pers. Med., 15.","DOI":"10.3390\/jpm15010036"},{"key":"ref_5","unstructured":"American Society of Breast Surgeons (2024). Resource Guide: Surgical Management of Benign or High-Risk Lesions, American Society of Breast Surgeons."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"n71","DOI":"10.1136\/bmj.n71","article-title":"The PRISMA 2020 statement: An updated guideline for reporting systematic reviews","volume":"372","author":"Page","year":"2021","journal-title":"BMJ"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"109579","DOI":"10.1016\/j.ejso.2025.109579","article-title":"Management of B3 breast lesions: Potential clinical implications from a retrospective study conducted in an accredited Breast Unit following the 2024 EUSOMA guidelines","volume":"51","author":"Corsi","year":"2025","journal-title":"Eur. J. Surg. Oncol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"9511","DOI":"10.1007\/s00330-021-08009-2","article-title":"Clinical value of radiomics and machine learning in breast ultrasound: A multicenter study for differential diagnosis of benign and malignant lesions","volume":"31","author":"Romeo","year":"2021","journal-title":"Eur. Radiol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Hussain, S., Lafarga-Osuna, Y., Ali, M., Naseem, U., Ahmed, M., and Tamez-Pe\u00f1a, J.G. (2023). Deep learning, radiomics and radiogenomics applications in digital breast tomosynthesis: A systematic review. BMC Bioinform., 24.","DOI":"10.1186\/s12859-023-05515-6"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"TR01","DOI":"10.1088\/1361-6560\/ac7d8f","article-title":"Machine learning for multi-parametric breast MRI: Radiomics-based approaches for lesion classification","volume":"67","author":"Altabella","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"101719","DOI":"10.1016\/j.xcrm.2024.101719","article-title":"Radiomics in breast cancer: Current advances and future directions","volume":"5","author":"Qi","year":"2024","journal-title":"Cell Rep. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"51","DOI":"10.7326\/M18-1376","article-title":"for the PROBAST Group. PROBAST: A tool to assess risk of bias and applicability of prediction model studies","volume":"170","author":"Wolff","year":"2019","journal-title":"Ann. Intern. Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"W1","DOI":"10.7326\/M18-1377","article-title":"PROBAST: Explanation and elaboration","volume":"170","author":"Moons","year":"2019","journal-title":"Ann. Intern. Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI: Updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","article-title":"The meaning and use of the area under a receiver operating characteristic (ROC) curve","volume":"143","author":"Hanley","year":"1982","journal-title":"Radiology"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1148\/radiology.148.3.6878708","article-title":"A method of comparing the areas under ROC curves derived from the same cases","volume":"148","author":"Hanley","year":"1983","journal-title":"Radiology"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/0197-2456(86)90046-2","article-title":"Meta-analysis in clinical trials","volume":"7","author":"DerSimonian","year":"1986","journal-title":"Control. Clin. Trials"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"IntHout, J., Ioannidis, J.P.A., and Borm, G.F. (2014). The Hartung\u2013Knapp\u2013Sidik\u2013Jonkman method for random effects meta-analysis is straightforward and considerably outperforms the standard DerSimonian\u2013Laird method. BMC Med. Res. Methodol., 14.","DOI":"10.1186\/1471-2288-14-25"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"R\u00f6ver, C., Knapp, G., and Friede, T. (2015). Hartung\u2013Knapp\u2013Sidik\u2013Jonkman approach and its modification for random-effects meta-analysis with few studies. BMC Med. Res. Methodol., 15.","DOI":"10.1186\/s12874-015-0091-1"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1136\/bmj.315.7109.629","article-title":"Bias in meta-analysis detected by a simple, graphical test","volume":"315","author":"Egger","year":"1997","journal-title":"BMJ"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v036.i03","article-title":"Conducting meta-analyses in R with the metafor package","volume":"36","author":"Viechtbauer","year":"2010","journal-title":"J. Stat. Softw."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"810","DOI":"10.1148\/radiol.2017170549","article-title":"High-Risk Breast Lesions: A Machine Learning Model to Predict Pathologic Upgrade and Reduce Unnecessary Surgical Excision","volume":"286","author":"Bahl","year":"2018","journal-title":"Radiology"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1200\/CCI.18.00083","article-title":"Prediction of Atypical Ductal Hyperplasia Upgrades Through a Machine Learning Approach to Reduce Unnecessary Surgical Excisions","volume":"2","author":"Harrington","year":"2018","journal-title":"JCO Clin. Cancer Inform."},{"key":"ref_24","first-page":"260","article-title":"Prediction of malignancy upgrade rate in high-risk breast lesions using an artificial intelligence model: A retrospective study","volume":"29","author":"Aslan","year":"2023","journal-title":"Diagn. Interv. Radiol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1533033820916191","DOI":"10.1177\/1533033820916191","article-title":"The application of radiomics in breast MRI: A review","volume":"19","author":"Ye","year":"2020","journal-title":"Technol. Cancer Res. Treat."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/1\/75\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T03:17:52Z","timestamp":1766719072000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/1\/75"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,25]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["diagnostics16010075"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16010075","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,25]]}}}